A New GNSS-R Altimetry Algorithm Based on Machine Learning Fusion Model and Feature Optimization to Improve the Precision of Sea Surface Height Retrieval

Abstract

The global navigation satellite system reflectometer (GNSS-R) can improve the observation and inversion of mesoscale by increasing the spatial coverage of ocean surface observations. The traditional retracking method is an empirical model with lower accuracy and condenses the Delay-Doppler Map information to a single scalar metric cannot completely represent the sea surface height (SSH) information. Firstly, to use multi-dimensional inputs for SSH retrieval, this paper constructs a new machine learning weighted average fusion feature extraction method based on the machine learning fusion model and feature extraction, which takes airborne delay waveform (DW) data as input and SSH as output. R2-Ranking method is used for weighted fusion, and the weights are distributed by the coefficient of determination of cross validation on the training set. Moreover, based on the airborne delay waveform data set, three features that are sensitive to the height of the sea surface are constructed, including the delay of the 70% peak correlation power (PCP70), the waveform leading edge peak first derivative (PFD), and the leading edge slope (LES). The effect of feature sets with varying levels of information details are analyzed as well. Secondly, the global average sea surface DTU15, which has been corrected by tides, is used to verify the reliability of the new machine learning weighted average fusion feature extraction method. The results show that the best retrieval performance can be obtained by using DW, PCP70 and PFD features. Compared with the DTU15 model, the root mean square error is about 0.23 m, and the correlation coefficient is about 0.75. Thirdly, the retrieval performance of the new machine learning weighted average fusion feature extraction method and the traditional single-point re-tracking method are compared and analyzed. The results show that the new machine learning weighted average fusion feature extraction method can effectively improve the precision of SSH retrieval, in which the mean absolute error is reduced by 63.1 and 59.2% respectively, and the root mean square error is reduced by 63.3 and 61.8% respectively; The correlation coefficient increased by 31.6 and 44.2% respectively. This method will provide the theoretical method support for the future GNSS-R SSH altimetry verification satellite.

Improving the SSH Retrieval Precision of Spaceborne GNSS-R Based on a New Grid Search Multihidden Layer Neural Network Feature Optimization Method

“…The validation model was composed of the DTU18 global mean sea surface (DTU18 MSS) model developed by the Technical University of Denmark and the TPXO8 global ocean tide model provided by Oregon State University (OSU) [31,32]. The SSH obtained from the validation model can be expressed as [11]:…”

“…The dimension of the filtered IDW dataset was reduced from 128 to 18. Additionally, the Principal Component Analysis (PCA) [11] method was used to extract the 15-dimensional feature sets with a cumulative contribution rate of 95% as the final IDW dataset. TDS-1 spaceborne IDW data are a collection of a 128-dimensional dataset.…”

“…(a) The delay of the peak correlation power (PCP): This feature takes the specular reflection delay at the peak correlation power. The peak correlation power is defined as [11]:…”

“…In 1993, Martin-Neira initially introduced GNSS-R technology to ocean altimetry [8]. This technology has been successfully verified on various platforms, including ground [9], airborne [10][11][12], and spaceborne [13][14][15]. Compared with the traditional radar altimeters, the GNSS-R altimeter has the advantages of being low-cost and having multiple signal sources and high temporal-spatial resolution [16,17].…”

“…Compared with the DTU15 validation model, the mean absolute difference (MAD) and the Pearson correlation coefficient (PCC) equal 0.25 m and 0.75, respectively. This study successfully applied ML algorithms to the field of GNSS-R ocean altimetry [11].…”